LM...LLM...Generative-AI...Diffusion-Models...Hallucination...Prompt-Engineering...Zero-shot-Prompting...Context-Window...Matryoshka- Embeddings...AGI...Annotation...ASI...Bias...Bot...Chatbot...Completions...Conversational AI...GPT...Hallucination...Inference...Model...NLP...Prompt...Reinforcement Learning...RAG...Training...Zero-Shot Learning
Memory...Indexes...Chains...Agents...Temperature...Tokens...Text-Span...Training-Data...Epoch...Batch-Size...Gradient-Descent...Learning-Rate...Loss-Function...Overfitting...Regularization...Backpropagation...Latency...Throughput...Fine-tuning...Prompt...Context-Window...Beam-Search...Greedy-Search...Softmax...Sampling...Tokenization...Attention-Mechanism
Transformers...Encoder...Positional-Encoder...Decoder...CLM...MLM...Vision-Transformer...Embeddings...Pre-Training...Finetuning...Instruction-Tuning...PEFT...Few-shot Learning...Parameters...Sematic Network...Tuning
Pruning...Quantization...Distillation...Low-rank-factorization...Knowledge-Distillation...Tensor-Decomposition...Weight-Sharing...Transfer-Learning...Binary-and-Ternary-Networks...Network-Slimming...Structured-Pruning...Sparse-Representation...Parameter-Sharing...Dynamic-Network-Surgery...Deep-Compression...Filter-Pruning...NAS...Feature-Map-Reuse...Energy-Aware-Pruning...Data-Free-Quantization...Layer-Fusion
RAG...RAG...Retriever...Generator...Knowledge-base...Query...Document...Embedding...Vector-database...Relevance-score...Context-window...Prompt-Engineering...Fine-tuning...Chunking...Indexing...Latency...Semantic-search...Token...Dense-retrieval...Sparse-retrieval...Hybrid-search...Reranking...Zero-shot-learning...Few-shot-learning...Corpus...Cross-encoder...Bi-encoder...Distillation...Attention-mechanism...Transform...BERT...GPT...T5...Cosine-similarity...Euclidean-distance...FAISS...Sentence-BERT...BM25...TF-IDF...LSH(Locality-Sensitive-Hashing)...HNSW...IVFPQ...IVF...Product-Quantization...Coarse-Quantizer...Residual-Vector...Subvector...Codebook...Centroid...Nprobe...Compression-Ratio...Negative-Sampling...Prompt-Template...Retrieval-Depth...Passage-Ranking...Query-Expansion...Document-Compression...Ensemble-Method...Multi-hop-Reasoning...Semantic-Caching...Contrastive-Learning...Zero-shot-Retrieval
Human-Eval...MMLU...MTEB...BIG-bench...Chatbot Arena...MT-Bench...GLUE...Super-Glue...BABILong...ARC...HellaSwag...MBPP...SWE-Bench...NIAH...MultiHop-RAG...NIAN...GQPA...MATH...MSGM...DROP...GSM8K
Response-Completeness...Text-Similarity...Question-Answering-Accuracy...Relevance...Hallucination-Index...Toxicity...Task-Specific...Grammer-and-Syntax...Truthfulness...Summary-Capability...Problem-Solving...Coherence...Diversity...Engagement...Empathy...Fairness...Robustness...Scalibity...Efficiency
Contributions are welcome! Please check out contributing guidelines and feel free to open a pull request.